How to Set Up and Use PromethAI: Your Personalized Decision-Making Assistant

October 29, 2020

Welcome to the world of PromethAI, an open-source framework designed to help you navigate decision-making by providing personalized goals and executing them seamlessly. This AI agent is an ally in streamlining your choices, particularly focusing on food, but it’s versatile enough to be adapted to various domains. Let’s explore how to get started with this innovative tool, along with some troubleshooting tips!

What is PromethAI?

PromethAI is a Python-based project that recommends choices based on user goals and preferences, modifying its recommendations according to user feedback. This smart assistant uses decision trees to ensure efficient navigation through your choices.

Features of PromethAI

Optimized for Autonomous Agents
Personalization for each user
Support for asynchronous operations
Integration with multiple Vector DBs through Langchain
Low latency for swift responses
Easy to use and deploy

Setting Up PromethAI

Download the repository:

git clone https://github.com/topoteretes/PromethAI-Backend.git

Navigate to the directory:
```
cd PromethAI-Backend
```
Create a copy of the environment file:
```
cp .env.template .env
```
Add your OpenAI API Key, Google key, and Custom search engine ID in the .env file.
Install Docker and Docker Compose (if not already installed). Instructions can be found here.
Run the following command to start PromethAI:
```
docker-compose up promethai --build
```
Visit localhost:3000 in your browser, and you should see PromethAI running.

Understanding How PromethAI Works

To visualize the functionality of PromethAI, imagine a chef in a kitchen. Each ingredient represents data about user preferences. When a user provides a prompt (like wanting a healthy chicken meal), the chef (our AI) processes this input, rummaging through ingredients (data) to create a dish (solution) based on the kitchen’s (system’s) capabilities and past experiences (memory). Finally, the chef prepares the meal (generates the output) and keeps track of what was used for future reference (stores in the database).

Using PromethAI

docker-compose build promethai

After launching the app, you can interact with the API using CURL requests. Here’s an example of an endpoint request:

curl --location --request POST http://0.0.0.0:8000/recipe-request --header "Content-Type: application/json" --data-raw '{ "user_id": 659, "session_id": 459, "model_speed": "slow", "prompt": "I would like a healthy chicken meal over $125" }'

Troubleshooting PromethAI

If you encounter any issues while using PromethAI, here are some troubleshooting ideas:

Docker Errors: Ensure Docker is properly installed and the service is running.
API Requests Fail: Check that your CURL command is formatted correctly and that the server is running on the specified port.
Missing Environment Variables: Double-check that you’ve correctly added all required keys in the .env file.

For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.

Conclusion

At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.